Completely non-invasive prediction of IDH mutation status based on preoperative native CT images

Abstract The isocitrate dehydrogenase (IDH) mutation status is one of the most important markers according to the 2021 WHO classification of CNS tumors. Preoperatively, this information is usually obtained based on invasive biopsies, contrast-enhanced MR images or PET images generated using radioact...

Full description

Saved in:
Bibliographic Details
Main Authors: Manfred Musigmann, Melike Bilgin, Sabriye Sennur Bilgin, Hermann Krähling, Walter Heindel, Manoj Mannil
Format: Article
Language:English
Published: Nature Portfolio 2024-11-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-024-77789-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846172031607898112
author Manfred Musigmann
Melike Bilgin
Sabriye Sennur Bilgin
Hermann Krähling
Walter Heindel
Manoj Mannil
author_facet Manfred Musigmann
Melike Bilgin
Sabriye Sennur Bilgin
Hermann Krähling
Walter Heindel
Manoj Mannil
author_sort Manfred Musigmann
collection DOAJ
description Abstract The isocitrate dehydrogenase (IDH) mutation status is one of the most important markers according to the 2021 WHO classification of CNS tumors. Preoperatively, this information is usually obtained based on invasive biopsies, contrast-enhanced MR images or PET images generated using radioactive tracers. However, the completely non-invasive determination of IDH mutation status using routinely acquired preoperative native CT images has hardly been investigated to date. In our study, we show that radiomics-based machine learning allows to determine IDH mutation status based on preoperative native CT images both with very high accuracy and completely non-invasively. Based on independent test data, we are able to correctly identify 91.1% of cases with an IDH mutation. Our final model, containing only six features, exhibits a high area under the curve of 0.847 and an excellent area under the precision-recall curve of 0.945. In the future, such models may be used for a completely non-invasive prediction of important genetic markers, potentially allowing treating physicians to reduce the number of biopsies and speed up further treatment planning.
format Article
id doaj-art-57d82ba3e5ee4a4ba1241daeed0f34e7
institution Kabale University
issn 2045-2322
language English
publishDate 2024-11-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-57d82ba3e5ee4a4ba1241daeed0f34e72024-11-10T12:19:45ZengNature PortfolioScientific Reports2045-23222024-11-0114111010.1038/s41598-024-77789-6Completely non-invasive prediction of IDH mutation status based on preoperative native CT imagesManfred Musigmann0Melike Bilgin1Sabriye Sennur Bilgin2Hermann Krähling3Walter Heindel4Manoj Mannil5University Clinic for Radiology, University Münster and University Hospital MünsterUniversity Clinic for Radiology, University Münster and University Hospital MünsterUniversity Clinic for Radiology, University Münster and University Hospital MünsterUniversity Clinic for Radiology, University Münster and University Hospital MünsterUniversity Clinic for Radiology, University Münster and University Hospital MünsterUniversity Clinic for Radiology, University Münster and University Hospital MünsterAbstract The isocitrate dehydrogenase (IDH) mutation status is one of the most important markers according to the 2021 WHO classification of CNS tumors. Preoperatively, this information is usually obtained based on invasive biopsies, contrast-enhanced MR images or PET images generated using radioactive tracers. However, the completely non-invasive determination of IDH mutation status using routinely acquired preoperative native CT images has hardly been investigated to date. In our study, we show that radiomics-based machine learning allows to determine IDH mutation status based on preoperative native CT images both with very high accuracy and completely non-invasively. Based on independent test data, we are able to correctly identify 91.1% of cases with an IDH mutation. Our final model, containing only six features, exhibits a high area under the curve of 0.847 and an excellent area under the precision-recall curve of 0.945. In the future, such models may be used for a completely non-invasive prediction of important genetic markers, potentially allowing treating physicians to reduce the number of biopsies and speed up further treatment planning.https://doi.org/10.1038/s41598-024-77789-6GliomaIDH mutation statusMachine learningArtificial intelligenceNeuroimagingComputed tomography (CT)
spellingShingle Manfred Musigmann
Melike Bilgin
Sabriye Sennur Bilgin
Hermann Krähling
Walter Heindel
Manoj Mannil
Completely non-invasive prediction of IDH mutation status based on preoperative native CT images
Scientific Reports
Glioma
IDH mutation status
Machine learning
Artificial intelligence
Neuroimaging
Computed tomography (CT)
title Completely non-invasive prediction of IDH mutation status based on preoperative native CT images
title_full Completely non-invasive prediction of IDH mutation status based on preoperative native CT images
title_fullStr Completely non-invasive prediction of IDH mutation status based on preoperative native CT images
title_full_unstemmed Completely non-invasive prediction of IDH mutation status based on preoperative native CT images
title_short Completely non-invasive prediction of IDH mutation status based on preoperative native CT images
title_sort completely non invasive prediction of idh mutation status based on preoperative native ct images
topic Glioma
IDH mutation status
Machine learning
Artificial intelligence
Neuroimaging
Computed tomography (CT)
url https://doi.org/10.1038/s41598-024-77789-6
work_keys_str_mv AT manfredmusigmann completelynoninvasivepredictionofidhmutationstatusbasedonpreoperativenativectimages
AT melikebilgin completelynoninvasivepredictionofidhmutationstatusbasedonpreoperativenativectimages
AT sabriyesennurbilgin completelynoninvasivepredictionofidhmutationstatusbasedonpreoperativenativectimages
AT hermannkrahling completelynoninvasivepredictionofidhmutationstatusbasedonpreoperativenativectimages
AT walterheindel completelynoninvasivepredictionofidhmutationstatusbasedonpreoperativenativectimages
AT manojmannil completelynoninvasivepredictionofidhmutationstatusbasedonpreoperativenativectimages